---
base_model:
- mllm-dev/gpt2_f_experiment_0
- mllm-dev/merge_diff_data_DROID
- mllm-dev/merge_diff_data_YELP
library_name: transformers
tags:
- mergekit
- merge

---
# merge_out

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [mllm-dev/gpt2_f_experiment_0](https://huggingface.co/mllm-dev/gpt2_f_experiment_0) as a base.

### Models Merged

The following models were included in the merge:
* [mllm-dev/merge_diff_data_DROID](https://huggingface.co/mllm-dev/merge_diff_data_DROID)
* [mllm-dev/merge_diff_data_YELP](https://huggingface.co/mllm-dev/merge_diff_data_YELP)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model:
  model:
    path: mllm-dev/gpt2_f_experiment_0
dtype: float16
merge_method: dare_linear
parameters:
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/merge_diff_data_DROID
    parameters:
      weight: 0.5
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/merge_diff_data_YELP
    parameters:
      weight: 0.5
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_0
```